© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2122
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MeasureSpec
    -0.66
    SuspendLayout
    -0.49
    /*
    -0.47
     With
    -0.44
     TestBed
    -0.44
    liches
    -0.43
    pended
    -0.42
    um
    -0.42
    تقاوى
    -0.42
    ending
    -0.41
    POSITIVE LOGITS
    tonode
    0.67
     disambiguazione
    0.67
    cestry
    0.65
    MethodType
    0.63
     AssemblyCulture
    0.61
    VideoCapture
    0.60
    richlet
    0.60
    CreateMap
    0.59
    writeFieldEnd
    0.58
    Jeografia
    0.56
    Activations Density 0.002%

    No Known Activations